Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    database code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kate
    -0.07
     rat
    -0.07
     corps
    -0.06
     Marvin
    -0.06
    Face
    -0.06
     ケ
    -0.06
    .For
    -0.06
    Kate
    -0.06
     PLAN
    -0.06
     Daniels
    -0.06
    POSITIVE LOGITS
    告
    0.07
    oufl
    0.07
     desarroll
    0.07
     pocit
    0.06
    adní
    0.06
    /config
    0.06
     ​​
    0.06
    나요
    0.06
    igInteger
    0.06
     geil
    0.06
    Act Density 0.052%

    No Known Activations